Reinforcement learning· 2018
Addressing Function Approximation Error in Actor-Critic Methods
On the reading lists
- #26 in Reinforcement learning (2026 edition)
Why it matters
Introduced twin critics and delayed updates to reduce overestimation in continuous control.
Condensed from the expert lists' notes.
The record
- First released
- 2018 (from arXiv 1802.09477)
- Citations
- 7,671 citations, as counted by Papers With Code (CC BY-SA 4.0)
- Named by
- both expert lists
- Score
- 0.334 · computed rank 519 · consensus 0.15, must-read 0, citations percentile 0.826 (2010s · reinforcement-learning), awards 0, existing lists 0. Method
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.